Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13302
On x86 and x86-64, it is possible that page tables are shared beween
shared mappings backed by hugetlbfs. As part of this,
page_table_shareable() checks a pair of vma->vm_flags and they must match
if they are to be shared. All VMA flags are taken into account, including
VM_LOCKED.
The problem is that VM_LOCKED is cleared on fork(). When a process with a
shared memory segment forks() to exec() a helper, there will be shared
VMAs with different flags. The impact is that the shared segment is
sometimes considered shareable and other times not, depending on what
process is checking.
What happens is that the segment page tables are being shared but the
count is inaccurate depending on the ordering of events. As the page
tables are freed with put_page(), bad pmd's are found when some of the
children exit. The hugepage counters also get corrupted and the Total and
Free count will no longer match even when all the hugepage-backed regions
are freed. This requires a reboot of the machine to "fix".
This patch addresses the problem by comparing all flags except VM_LOCKED
when deciding if pagetables should be shared or not for hugetlbfs-backed
mapping.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: <starlight@binnacle.cx>
Cc: Eric B Munson <ebmunson@us.ibm.com>
Cc: Adam Litke <agl@us.ibm.com>
Cc: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This will test the automatic aperture enlargement code. This is
important because only very few devices will ever trigger this code
path. So force it under CONFIG_IOMMU_STRESS.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Disabling the round-robin allocator results in reusing the same
dma-addresses again very fast. This is a good test if the iotlb flushing
is working correctly.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch makes sure no reserved addresses are allocated in an dma_ops
domain when the aperture is increased dynamically.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Simplify the code a little bit by using the same unit for all address
space related state in the dma_ops domain structure.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch changes the AMD IOMMU address allocator to allow up to 32
aperture ranges per dma_ops domain.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The code will be required when the aperture size increases dynamically
in the extended address allocator.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch makes sure that no function required for suspend/resume of
AMD IOMMU driver is thrown away after boot.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Current hardware uses msi instead of msi-x so this code it not necessary
and can not be tested. The best thing is to drop this code.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch restructures the AMD IOMMU initialization code to initialize
all hardware registers with one single function call.
This is helpful for suspend/resume support.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This patch introduces the for_each_iommu and for_each_iommu_safe macros
to simplify the developers life when having to iterate over all AMD
IOMMUs in the system.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Some drivers may use the dma api during ->remove which will
cause a protection domain to get reattached to a device. Delay the
detach until after the driver is completely unbound.
[ joro: added a little merge helper ]
[ Impact: fix too early device<->domain removal ]
Signed-off-by: Chris Wright <chrisw@redhat.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The bug never triggered. But it should be fixed to protect against
broken ACPI tables in the future.
[ Impact: protect against broken ivrs acpi table ]
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The devid parameter to set_dev_entry_from_acpi is the requester ID
rather than the device ID since it is used to index the IOMMU device
table. The handling of IVHD_DEV_ALIAS used to pass the device ID.
This patch fixes it to pass the requester ID.
[ Impact: fix setting the wrong req-id in acpi-table parsing ]
Signed-off-by: Neil Turton <nturton@solarflare.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The variable amd_iommu_last_bdf holds the maximum bdf of any device
controlled by an IOMMU, so the number of device entries needed is
amd_iommu_last_bdf+1. The function tbl_size used amd_iommu_last_bdf
instead. This would be a problem if the last device were a large
enough power of 2.
[ Impact: fix amd_iommu_last_bdf off-by-one error ]
Signed-off-by: Neil Turton <nturton@solarflare.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This Kconfig option is intended to enable various code paths or
parameters in IOMMU implementations to stress test the code and/or the
hardware. This can also be done by disabling optimizations in the code
when this option is switched on.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Add information about device memory mapping requirements for the IOMMU
as described in the IVRS ACPI table to the kernel log if amd_iommu_dump
was specified on the kernel command line.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Add information about devices belonging to an IOMMU as described in the
IVRS ACPI table to the kernel log if amd_iommu_dump was specified on the
kernel command line.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Add information about IOMMU devices described in the IVRS ACPI table to
the kernel log if amd_iommu_dump was specified on the kernel command
line.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
This kernel parameter will be useful to get some AMD IOMMU related
information in dmesg that is not necessary for the default user but may
be helpful in debug situations.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The *fence instructions were moved to vsyscall_64.c by commit
cb9e35dce9. But this breaks the
vDSO, because vread methods are also called from there.
Besides, the synchronization might be unnecessary for other
time sources than TSC.
[ Impact: fix potential time warp in VDSO ]
Signed-off-by: Petr Tesarik <ptesarik@suse.cz>
LKML-Reference: <9d0ea9ea0f866bdc1f4d76831221ae117f11ea67.1243241859.git.ptesarik@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@kernel.org>
instead of declaring one variant as an inline function...
because other case is a variable
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4A13B344.7030307@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: avoid back to back on_each_cpu in cpa_flush_array
x86, relocs: ignore R_386_NONE in kernel relocation entries
Cleanup cpa_flush_array() to avoid back to back on_each_cpu() calls.
[ Impact: optimizes fix 0af48f42df ]
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Slightly modified by trenn@suse.de -> only do this on fam 10h and fam 11h.
Currently powernow-k8 determines CPU frequency from ACPI PSS objects, but
according to AMD family 11h BKDG this frequency is just a rounded value:
"CoreFreq (MHz) = The CPU COF specified by MSRC001_00[6B:64][CpuFid]
rounded to the nearest 100 Mhz."
As a consequnce powernow-k8 reports wrong CPU frequency on some systems,
e.g. on Turion X2 Ultra:
powernow-k8: Found 1 AMD Turion(tm)X2 Ultra DualCore Mobile ZM-82
processors (2 cpu cores) (version 2.20.00)
powernow-k8: 0 : pstate 0 (2200 MHz)
powernow-k8: 1 : pstate 1 (1100 MHz)
powernow-k8: 2 : pstate 2 (600 MHz)
But this is wrong as frequency for Pstate2 is 550 MHz. x86info reports it
correctly:
#x86info -a |grep Pstate
...
Pstate-0: fid=e, did=0, vid=24 (2200MHz)
Pstate-1: fid=e, did=1, vid=30 (1100MHz)
Pstate-2: fid=e, did=2, vid=3c (550MHz) (current)
Solution is to determine the frequency directly from Pstate MSRs instead
of using rounded values from ACPI table.
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Dave Jones <davej@redhat.com>
- Make the message shorter and easier to grep for
- Use printk_once instead of WARN_ONCE (functionality of these was mixed)
Signed-off-by: Thomas Renninger <trenn@suse.de>
Cc: Langsdorf, Mark <mark.langsdorf@amd.com>
Signed-off-by: Dave Jones <davej@redhat.com>
arch/x86/kernel/cpu/cpufreq/powernow-k7.c:172: warning: 'invalidate_entry' defined but not used
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Dave Jones <davej@redhat.com>
Some atom procs don't do freq scaling (such as the atom 330 on my own
littlefalls2 board). By adding the atom family here, we at least get
the benefit of passive cooling in a thermal emergency. Not sure how
to see that its actually helping any, but the driver does bind and
claim its functioning on my atom 330.
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Dave Jones <davej@redhat.com>
For relocatable 32bit kernels, boot/compressed/relocs.c processes
relocation entries in the kernel image and appends it to the kernel
image such that boot/compressed/head_32.S can relocate the kernel.
The kernel image is one statically linked object and only uses two
relocation types - R_386_PC32 and R_386_32, of the two only the latter
needs massaging during kernel relocation and thus handled by relocs.
R_386_PC32 is ignored and all other relocation types are considered
error.
When the target of a relocation resides in a discarded section,
binutils doesn't throw away the relocation record but nullifies it by
changing it to R_386_NONE, which unfortunately makes relocs fail.
The problem was triggered by yet out-of-tree x86 stack unwind patches
but given the binutils behavior, ignoring R_386_NONE is the right
thing to do.
The problem has been tracked down to binutils behavior by Jan Beulich.
[ Impact: fix build with certain binutils by ignoring R_386_NONE ]
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jan Beulich <JBeulich@novell.com>
Cc: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <4A1B8150.40702@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
* 'kvm-updates/2.6.30' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: Fix PDPTR reloading on CR4 writes
KVM: Make paravirt tlb flush also reload the PAE PDPTRs
The processor is documented to reload the PDPTRs while in PAE mode if any
of the CR4 bits PSE, PGE, or PAE change. Linux relies on this
behaviour when zapping the low mappings of PAE kernels during boot.
The code already handled changes to CR4.PAE; augment it to also notice changes
to PSE and PGE.
This triggered while booting an F11 PAE kernel; the futex initialization code
runs before any CR3 reloads and writes to a NULL pointer; the futex subsystem
ended up uninitialized, killing PI futexes and pulseaudio which uses them.
Cc: stable@kernel.org
Signed-off-by: Avi Kivity <avi@redhat.com>
The paravirt tlb flush may be used not only to flush TLBs, but also
to reload the four page-directory-pointer-table entries, as it is used
as a replacement for reloading CR3. Change the code to do the entire
CR3 reloading dance instead of simply flushing the TLB.
Cc: stable@kernel.org
Signed-off-by: Avi Kivity <avi@redhat.com>
Remap percpu allocator has subtle bug when combined with page
attribute changing. Remap percpu allocator aliases PMD pages for the
first chunk and as pageattr doesn't know about the alias it ends up
updating page attributes of the original mapping thus leaving the
alises in inconsistent state which might lead to subtle data
corruption. Please read the following threads for more information:
http://thread.gmane.org/gmane.linux.kernel/835783
The following is the proposed fix which teaches pageattr about percpu
aliases.
http://thread.gmane.org/gmane.linux.kernel/837157
However, the above changes are deemed too pervasive for upstream
inclusion for 2.6.30 release, so this patch essentially disables
the remap allocator for the time being.
Signed-off-by: Tejun Heo <tj@kernel.org>
LKML-Reference: <4A1A0A27.4050301@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
cpa_flush_array seems to prefer wbinvd() over clflush at 4M threshold.
clflush needs to be done on only one CPU as per instruction definition.
wbinvd() however, should be done on all CPUs.
[ Impact: fix missing flush which could cause data corruption ]
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
wbinvd is supported on all CPUs 486 or later. But,
pageattr.c is checking x86_model >= 4 before wbinvd(), which looks like
an oversight bug. It was first introduced at one place by changeset
d7c8f21a8c and got copied over to second
place in the same file later.
[ Impact: fix missing cache flush on early-model CPUs, potential data corruption ]
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Introduce "noxsave" boot parameter which will disable the cpu's xsave/xrstor
capabilities. Useful for debugging and working around xsave related issues.
[ Impact: make it possible to debug problems in the field ]
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Remove ACPI 3 E820 extended memory attributes support. At least one
vendor actively set all the flags to zero, but left ECX on return at
24. This bug may be present in other BIOSes.
The breakage functionally means the ACPI 3 flags are probably
completely useless, and that no OS any time soon is going to rely on
their existence. Therefore, drop support completely. We may want to
revisit this question in the future, if we find ourselves actually
needing the flags.
This reverts all or part of the following checkins:
cd670599b7c549e71d07
However, retain the part from the latter commit that copies e820 into
a temporary buffer; that is an unrelated BIOS workaround. Put in a
comment to explain that part.
See https://bugzilla.redhat.com/show_bug.cgi?id=499396 for some
additional information.
[ Impact: detect all memory on affected machines ]
Reported-by: Thomas J. Baker <tjb@unh.edu>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Len Brown <len.brown@intel.com>
Cc: Chuck Ebbert <cebbert@redhat.com>
Cc: Kyle McMartin <kmcmartin@redhat.com>
Cc: Matt Domsch <matt_domsch@dell.com>
x86: DMI match for the Sony VGN-Z540N as it needs BIOS reboot,
see:
http://bugzilla.kernel.org/show_bug.cgi?id=12901
[ Impact: fix hung reboot on certain systems ]
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Cc: Len Brown <lenb@kernel.org>
LKML-Reference: <1242963350.32574.53.camel@rzhang-dt>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Correct the calculation of ZO_INIT_SIZE (the amount of memory we need
during decompression). One symbol (ZO_startup_32) was missing from
zoffset.h, and another (ZO_z_extract_offset) was misspelled.
[ Impact: build fix ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Peter bisected that:
| commit b9c61b7007
| Date: Wed May 6 10:10:06 2009 -0700
|
| x86/pci: update pirq_enable_irq() to setup io apic routing
|
| So we can set io apic routing only when enabling the device irq.
wrecked his opteron box, ata1 interrupts fail to get through.
ata1 is using irq 11:
[ 1.451839] sata_svw 0000:01:0e.0: version 2.3
[ 1.456333] sata_svw 0000:01:0e.0: PCI INT A -> GSI 11 (level, low) -> IRQ 11
[ 1.463639] scsi0 : sata_svw
[ 1.466949] scsi1 : sata_svw
[ 1.470022] scsi2 : sata_svw
[ 1.473090] scsi3 : sata_svw
[ 1.476112] ata1: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe000 irq 11
[ 1.483490] ata2: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe100 irq 11
[ 1.490870] ata3: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe200 irq 11
[ 1.498247] ata4: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe300 irq 11
that pin is overlapped with pin with legacy ones.
We should not set bits in pin_programmed here, so that those bit could
be set later via io_apic_set_pci_routing().
[ Impact: fix boot hang on certain systems ]
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Yinghai Lu <yinghai.lu@kernel.org>
Tested-by: Peter Zijlstra <peterz@infradead.org>
Cc: Jack Steiner <steiner@sgi.com>
LKML-Reference: <4A119990.9020606@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing: Append prompt in /debug/tracing/README file
x86/function-graph: fix constraint for recording old return value
Len expressed concern that the update_mptable feature has
side-effects on the ACPI code.
Make it sure explicitly that the code only ever gets called if
the (default disabled) update_mptable boot quirk option is
disabled.
[ Impact: isolate the update_mptable feature from ACPI code more ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Len Brown <lenb@kernel.org>
LKML-Reference: <4A0DC832.5090200@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
To get all device irq routing and to save them.
This is basically an implicit pci=routeirq enablement if (and on if)
the update_mptable boot option (which is off by default) has been
specified.
[ Impact: extend the update_mptable boot opion's scope ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
LKML-Reference: <4A0DB7B4.4060702@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Jack found a boot crash on a system which doesn't have memory on node0.
It turns out with recent per_cpu changes, node_number for BSP will always
be 0, and it is not consistent to cpu_to_node() that might set it to a
different (nearer) node already.
aka when numa_set_node() for node0 is called early before per_cpu area is
setup:
two places touched that per_cpu(node_number,):
1. in cpu/common.c::cpu_init() and it is not for BP
| #ifdef CONFIG_NUMA
| if (cpu != 0 && percpu_read(node_number) == 0 &&
| cpu_to_node(cpu) != NUMA_NO_NODE)
| percpu_write(node_number, cpu_to_node(cpu));
| #endif
for BP: traps_init ==> cpu_init
for AP: start_secondary ==> cpu_init
2. cpu/intel.c or amd.c::srat_detect_node via numa_set_node()
for BP: check_bugs ==> identify_boot_cpu ==> identify_cpu()
that is rather later before numa_node_id() is used for BP...
for AP: start_secondary => smp_callin => smp_store_cpu_info() =>
=> identify_secondary_cpu => identify_cpu()
so try to set that for BP earlier in setup_per_cpu_areas(), and
don't bother to set that for APs there (it will be updated later
and will be used later)
(and don't mess the 0 before the copying BP per_cpu data to APs)
[ Impact: fix boot crash on memoryless node-0 ]
Reported-and-tested-by: Jack Steiner <steiner@sgi.com>
Cc: Tejun Heo <htejun@gmail.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4A0C4A02.7050401@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Recently there were some changes to the meaning of node_possible_map,
and it is quite strange:
- the node without memory would be set in node_possible_map
- but some node with less NODE_MIN_SIZE will be kicked out of node_possible_map.
fix it by adding strict_setup_node_bootmem().
Also, remove unparse_node().
so result will be:
1. cpu_to_node() will return online node only (nearest one)
2. apicid_to_node() still returns the node that could be not online but is set
in node_possible_map.
3. node_possible_map will include nodes that mem on it are less NODE_MIN_SIZE
v2: after move_cpus_to_node change.
[ Impact: get node_possible_map right ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Tested-by: Jack Steiner <steiner@sgi.com>
LKML-Reference: <4A0C49BE.6080800@kernel.org>
[ v3: various small cleanups and comment clarifications ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
after:
| commit b263295dbf
| Author: Christoph Lameter <clameter@sgi.com>
| Date: Wed Jan 30 13:30:47 2008 +0100
|
| x86: 64-bit, make sparsemem vmemmap the only memory model
we don't have MEMORY_HOTPLUG_RESERVE anymore.
Historically, x86-64 had an architecture-specific method for memory hotplug
whereby it scanned the SRAT for physical memory ranges that could be
potentially used for memory hot-add later. By reserving those ranges
without physical memory, the memmap would be allocated and left dormant
until needed. This depended on the DISCONTIG memory model which has been
removed so the code implementing HOTPLUG_RESERVE is now dead.
This patch removes the dead code used by MEMORY_HOTPLUG_RESERVE.
(Changelog authored by Mel.)
v2: updated changelog, and remove hotadd= in doc
[ Impact: remove dead code ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: Mel Gorman <mel@csn.ul.ie>
Workflow-found-OK-by: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <4A0C4910.7090508@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Merge reason: sync up to -rc6 which has changes to mm/ which we are
going to touch in the commits to follow as well.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
should not call that if apic is disabled.
[ Impact: fix crash on certain UP configs ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
LKML-Reference: <4A09CCBB.2000306@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
according to Ingo, io_apic irq-setup related functions have too many
parameters with a repetitive signature.
So reduce related funcs to get less params by passing a pointer
to a newly defined io_apic_irq_attr structure.
v2: io_apic_irq ==> irq_attr
triggering ==> trigger
v3: add set_io_apic_irq_attr
[ Impact: cleanup ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Len Brown <lenb@kernel.org>
LKML-Reference: <4A08ACD3.2070401@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Xiaohui Xin and some other folks at Intel have been looking into what's
behind the performance hit of paravirt_ops when running native.
It appears that the hit is entirely due to the paravirtualized
spinlocks introduced by:
| commit 8efcbab674
| Date: Mon Jul 7 12:07:51 2008 -0700
|
| paravirt: introduce a "lock-byte" spinlock implementation
The extra call/return in the spinlock path is somehow
causing an increase in the cycles/instruction of somewhere around 2-7%
(seems to vary quite a lot from test to test). The working theory is
that the CPU's pipeline is getting upset about the
call->call->locked-op->return->return, and seems to be failing to
speculate (though I haven't seen anything definitive about the precise
reasons). This doesn't entirely make sense, because the performance
hit is also visible on unlock and other operations which don't involve
locked instructions. But spinlock operations clearly swamp all the
other pvops operations, even though I can't imagine that they're
nearly as common (there's only a .05% increase in instructions
executed).
If I disable just the pv-spinlock calls, my tests show that pvops is
identical to non-pvops performance on native (my measurements show that
it is actually about .1% faster, but Xiaohui shows a .05% slowdown).
Summary of results, averaging 10 runs of the "mmperf" test, using a
no-pvops build as baseline:
nopv Pv-nospin Pv-spin
CPU cycles 100.00% 99.89% 102.18%
instructions 100.00% 100.10% 100.15%
CPI 100.00% 99.79% 102.03%
cache ref 100.00% 100.84% 100.28%
cache miss 100.00% 90.47% 88.56%
cache miss rate 100.00% 89.72% 88.31%
branches 100.00% 99.93% 100.04%
branch miss 100.00% 103.66% 107.72%
branch miss rt 100.00% 103.73% 107.67%
wallclock 100.00% 99.90% 102.20%
The clear effect here is that the 2% increase in CPI is
directly reflected in the final wallclock time.
(The other interesting effect is that the more ops are
out of line calls via pvops, the lower the cache access
and miss rates. Not too surprising, but it suggests that
the non-pvops kernel is over-inlined. On the flipside,
the branch misses go up correspondingly...)
So, what's the fix?
Paravirt patching turns all the pvops calls into direct calls, so
_spin_lock etc do end up having direct calls. For example, the compiler
generated code for paravirtualized _spin_lock is:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq *0xffffffff805a5b30
<_spin_lock+22>: retq
The indirect call will get patched to:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq <__ticket_spin_lock>
<_spin_lock+20>: nop; nop /* or whatever 2-byte nop */
<_spin_lock+22>: retq
One possibility is to inline _spin_lock, etc, when building an
optimised kernel (ie, when there's no spinlock/preempt
instrumentation/debugging enabled). That will remove the outer
call/return pair, returning the instruction stream to a single
call/return, which will presumably execute the same as the non-pvops
case. The downsides arel 1) it will replicate the
preempt_disable/enable code at eack lock/unlock callsite; this code is
fairly small, but not nothing; and 2) the spinlock definitions are
already a very heavily tangled mass of #ifdefs and other preprocessor
magic, and making any changes will be non-trivial.
The other obvious answer is to disable pv-spinlocks. Making them a
separate config option is fairly easy, and it would be trivial to
enable them only when Xen is enabled (as the only non-default user).
But it doesn't really address the common case of a distro build which
is going to have Xen support enabled, and leaves the open question of
whether the native performance cost of pv-spinlocks is worth the
performance improvement on a loaded Xen system (10% saving of overall
system CPU when guests block rather than spin). Still it is a
reasonable short-term workaround.
[ Impact: fix pvops performance regression when running native ]
Analysed-by: "Xin Xiaohui" <xiaohui.xin@intel.com>
Analysed-by: "Li Xin" <xin.li@intel.com>
Analysed-by: "Nakajima Jun" <jun.nakajima@intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Xen-devel <xen-devel@lists.xensource.com>
LKML-Reference: <4A0B62F7.5030802@goop.org>
[ fixed the help text ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use standard msr-index.h's MSR declaration and no need to declare again.
[ Impact: cleanup, no object code change ]
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Use standard msr-index.h's MSR declaration and no need to declare again.
[ Impact: cleanup, no object code change ]
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Removed MTRR MSR from mtrr/mtrr.h as these are already declared in
msr-index.h and nobody is using them:
MTRRfix16K_A0000_MSR
MTRRfix4K_C8000_MSR
MTRRfix4K_D0000_MSR
MTRRfix4K_D8000_MSR
MTRRfix4K_E0000_MSR
MTRRfix4K_E8000_MSR
MTRRfix4K_F0000_MSR
MTRRfix4K_F8000_MSR
Use standard msr-index.h's MSR declaration and no need to declare again
[ Impact: cleanup, no object code change ]
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Use standard msr-index.h's MSR declaration and no need to declare again
[ Impact: cleanup, no object code change ]
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Use standard msr-index.h's MSR declaration and no need to declare again.
[ Impact: cleanup, no object code change ]
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Use standard msr-index.h's MSR declaration and no need to declare again.
[ Impact: cleanup, no object code change ]
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The treatment of the SP register is different on x86_64 and i386.
This is a regression fix that lived outside the mainline kernel from
2.6.27 to now. The regression was a result of the original merge
consolidation of the i386 and x86_64 archs to x86.
The incorrectly reported SP on i386 prevented stack tracebacks from
working correctly in gdb.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
If we return -1 in the ops->stack for the stacktrace saving, we end up
breaking out of the loop if the stack we are tracing is in the exception
stack. This causes traces like:
<idle>-0 [002] 34263.745825: raise_softirq_irqoff <-__blk_complete_request
<idle>-0 [002] 34263.745826:
<= 0
<= 0
<= 0
<= 0
<= 0
<= 0
<= 0
By returning "0" instead, the irq stack is saved as well, and we see:
<idle>-0 [003] 883.280992: raise_softirq_irqoff <-__hrtimer_star
t_range_ns
<idle>-0 [003] 883.280992:
<= hrtimer_start_range_ns
<= tick_nohz_restart_sched_tick
<= cpu_idle
<= start_secondary
<=
<= 0
<= 0
[ Impact: record stacks from interrupts ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
After upgrading from gcc 4.2.2 to 4.4.0, the function graph tracer broke.
Investigating, I found that in the asm that replaces the return value,
gcc was using the same register for the old value as it was for the
new value.
mov (addr), old
mov new, (addr)
But if old and new are the same register, we clobber new with old!
I first thought this was a bug in gcc 4.4.0 and reported it:
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=40132
Andrew Pinski responded (quickly), saying that it was correct gcc behavior
and the code needed to denote old as an "early clobber".
Instead of "=r"(old), we need "=&r"(old).
[Impact: keep function graph tracer from breaking with gcc 4.4.0 ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
mmu.c needs to #include module.h to prevent these warnings:
arch/x86/xen/mmu.c:239: warning: data definition has no type or storage class
arch/x86/xen/mmu.c:239: warning: type defaults to 'int' in declaration of 'EXPORT_SYMBOL_GPL'
arch/x86/xen/mmu.c:239: warning: parameter names (without types) in function declaration
[ Impact: cleanup ]
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Handle the misconfiguration where CONFIG_PHYSICAL_START is
incompatible with CONFIG_PHYSICAL_ALIGN. This is a configuration
error, but one which arises easily since Kconfig doesn't have the
smarts to express the true relationship between these two variables.
Hence, align __PHYSICAL_START the same way we align LOAD_PHYSICAL_ADDR
in <asm/boot.h>.
For non-relocatable kernels, this would cause the boot to fail.
[ Impact: fix boot failures for non-relocatable kernels ]
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
arch/x86/boot/compressed/misc.c contains several sanity checks on the
output address. Correct constraints that are no longer correct:
- the alignment test should be MIN_KERNEL_ALIGN on both 32 and 64
bits.
- the 64 bit maximum address was set to 2^40, which was the limit of
one specific x86-64 implementation. Change the test to 2^46, the
current Linux limit, and at least try to test the end rather than
the beginning.
- for non-relocatable kernels, test against LOAD_PHYSICAL_ADDR on both
32 and 64 bits.
[ Impact: fix potential boot failure due to invalid tests ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Ed found that on 32-bit, boot_cpu_physical_apicid is not read right,
when the mptable is broken.
Interestingly, actually three paths use/set it:
1. acpi: at that time that is already read from reg
2. mptable: only read from mptable
3. no madt, and no mptable, that use default apic id 0 for 64-bit, -1 for 32-bit
so we could read the apic id for the 2/3 path. We trust the hardware
register more than we trust a BIOS data structure (the mptable).
We can also avoid the double set_fixmap() when acpi_lapic
is used, and also need to move cpu_has_apic earlier and
call apic_disable().
Also when need to update the apic id, we'd better read and
set the apic version as well - so that quirks are applied precisely.
v2: make path 3 with 64bit, use -1 as apic id, so could read it later.
v3: fix whitespace problem pointed out by Ed Swierk
v5: fix boot crash
[ Impact: get correct apic id for bsp other than acpi path ]
Reported-by: Ed Swierk <eswierk@aristanetworks.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
LKML-Reference: <49FC85A9.2070702@kernel.org>
[ v4: sanity-check in the ACPI case too ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Merge reason: both topics modify the APIC code but were able to do it in
parallel so far. An upcoming patch generates a conflict so
merge them to avoid the conflict.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
With sparse memory, holes should not be marked present for memmap.
This patch makes sure sparsemem really works on SMP mode (!NUMA).
[ Impact: use less memory to map fragmented RAM, avoid boot-OOM/crash ]
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Sheng Yang <sheng.yang@intel.com>
LKML-Reference: <1242117600.22431.0.camel@sli10-desk.sh.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
<stdarg.h> is not needed by these files, remove them.
[ Impact: cleanup ]
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: akpm@linux-foundation.org
LKML-Reference: <20090512032956.5040.77055.sendpatchset@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Merge arch_align_stack() and arch_randomize_brk(), since
they are the same.
Tested on x86_64.
[ Impact: cleanup ]
Signed-off-by: Amerigo Wang <amwang@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Solve issues described in 6f66cbc630
in a way that doesn't resort to set_cpus_allowed();
* in fact, only collect_cpu_info and apply_microcode callbacks
must run on a target cpu, others will do just fine on any other.
smp_call_function_single() (as suggested by Ingo) is used to run
these callbacks on a target cpu.
* cleanup of synchronization logic of the 'microcode_core' part
The generic 'microcode_core' part guarantees that only a single cpu
(be it a full-fledged cpu, one of the cores or HT)
is being updated at any particular moment of time.
In general, there is no need for any additional sync. mechanism in
arch-specific parts (the patch removes existing spinlocks).
See also the "Synchronization" section in microcode_core.c.
* return -EINVAL instead of -1 (which is translated into -EPERM) in
microcode_write(), reload_cpu() and mc_sysdev_add(). Other suggestions
for an error code?
* use 'enum ucode_state' as return value of request_microcode_{fw, user}
to gain more flexibility by distinguishing between real error cases
and situations when an appropriate ucode was not found (which is not an
error per-se).
* some minor cleanups
Thanks a lot to Hugh Dickins for review/suggestions/testing!
Reference: http://marc.info/?l=linux-kernel&m=124025889012541&w=2
[ Impact: refactor and clean up microcode driver locking code ]
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Acked-by: Hugh Dickins <hugh@veritas.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Peter Oruba <peter.oruba@amd.com>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <1242078507.5560.9.camel@earth>
[ did some more cleanups ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
arch/x86/include/asm/microcode.h | 25 ++
arch/x86/kernel/microcode_amd.c | 58 ++----
arch/x86/kernel/microcode_core.c | 326 +++++++++++++++++++++-----------------
arch/x86/kernel/microcode_intel.c | 92 +++-------
4 files changed, 261 insertions(+), 240 deletions(-)
(~20 new comment lines)
A long ago, in days of yore, it all began with a god named Thor.
There were vikings and boats and some plans for a Linux kernel
header. Unfortunately, a single 8-bit field was used for bootloader
type and version. This has generally worked without *too* much pain,
but we're getting close to flat running out of ID fields.
Add extension fields for both type and version. The type will be
extended if it the old field is 0xE; the version is a simple MSB
extension.
Keep /proc/sys/kernel/bootloader_type containing
(type << 4) + (ver & 0xf) for backwards compatiblity, but also add
/proc/sys/kernel/bootloader_version which contains the full version
number.
[ Impact: new feature to support more bootloaders ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Update CONFIG_RELOCATABLE, CONFIG_PHYSICAL_START and
CONFIG_PHYSICAL_ALIGN to reflect the current defaults.
[ Impact: make defconfig match Kconfig defaults ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Update defconfigs to reflect current configuration files. No other
changes.
[ Impact: updates defconfigs to match what "make defconfig" generates ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Remove the EXPERIMENTAL tag from CONFIG_RELOCATABLE and make it the
default. Relocatable kernels have been used for a while now, and
should now have identical semantics to non-relocatable kernels when
loaded by a non-relocating bootloader.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Default CONFIG_PHYSICAL_START and CONFIG_PHYSICAL_ALIGN each to 16 MB,
so that both non-relocatable and relocatable kernels are loaded at
16 MB by a non-relocating bootloader. This is somewhat hacky, but it
appears to be the only way to do this that does not break some some
set of existing bootloaders.
We want to avoid the bottom 16 MB because of large page breakup,
memory holes, and ZONE_DMA. Embedded systems may need to reduce this,
or update their bootloaders to be aware of the new min_alignment field.
[ Impact: performance improvement, avoids problems on some systems ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Make the kernel_alignment field adjustable; this allows us to set it
to a large value (intended to be 16 MB to avoid ZONE_DMA contention,
memory holes and other weirdness) while a smart bootloader can still
force a loading at a lesser alignment if absolutely necessary.
Also export pref_address (preferred loading address, corresponding to
the link-time address) and init_size, the total amount of linear
memory the kernel will require during initialization.
[ Impact: allows better kernel placement, gives bootloader more info ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Remove a couple of lines of dead code from
arch/x86/boot/compressed/head_*.S; all of these update registers that
are dead in the current code.
[ Impact: cleanup ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Use ®s->sp instead of regs for getting the top of stack in kernel mode.
(on x86-64, regs->sp always points the top of stack)
[ Impact: Oprofile decodes only stack for backtracing on i386 ]
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
[ v2: rename the API to kernel_stack_pointer(), move variable inside ]
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: systemtap@sources.redhat.com
Cc: Harvey Harrison <harvey.harrison@gmail.com>
Cc: Jan Blunck <jblunck@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
LKML-Reference: <20090511210300.17332.67549.stgit@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix to prevent sched_mc_power_saving from being exported through sysfs
for multi-scoket single core system. Max cores should be always greater than
one (1). My earlier patch that introduced fix for not exporting
'sched_mc_power_saving' on laptops broke it on multi-socket single core
system. This fix addresses issue on both laptop and multi-socket single
core system.
Below are the Test results:
1. Single socket - multi-core
Before Patch: Does not export 'sched_mc_power_saving'
After Patch: Does not export 'sched_mc_power_saving'
Result: Pass
2. Multi Socket - single core
Before Patch: exports 'sched_mc_power_saving'
After Patch: Does not export 'sched_mc_power_saving'
Result: Pass
3. Multi Socket - Multi core
Before Patch: exports 'sched_mc_power_saving'
After Patch: exports 'sched_mc_power_saving'
[ Impact: make the sched_mc_power_saving control available more consistently ]
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Suresh B Siddha <suresh.b.siddha@intel.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090511143914.GB4853@dirshya.in.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use LOAD_PHYSICAL_ADDR instead of CONFIG_PHYSICAL_START in the 64-bit
decompression code, for equivalence with the 32-bit code.
[ Impact: cleanup, increases code similarity ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Make symbols from the main vmlinux, as opposed to just
compressed/vmlinux, available to header.S. Also, export a few
additional symbols.
This will be used in a subsequent patch to export the total memory
footprint of the kernel.
[ Impact: enable future enhancement ]
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
- the byte operand constraints were wrong for 32-bit
- the to-op's input operands weren't properly parenthesized
[ Impact: fix possible miscompilation or build failure ]
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
struct thread_struct::ip isn't used on x86_64, struct pt_regs::ip is used
instead.
kgdb should be reading 0 always, but I can't check it.
[ Impact: (potentially) reduce thread_struct size on 64-bit ]
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: containers@lists.linux-foundation.org
LKML-Reference: <20090503233015.GJ16631@x200.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
After commit 464d1a78fb aka
"[PATCH] i386: Convert i386 PDA code to use %fs"
%fs saved during context switch moved from thread_struct to pt_regs
and value on thread_struct became unused.
[ Impact: reduce thread_struct size on 32-bit ]
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: containers@lists.linux-foundation.org
LKML-Reference: <20090503232952.GI16631@x200.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
